{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0159932374954224, "min": 1.0159932374954224, "max": 2.8593382835388184, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9700.703125, "min": 9700.703125, "max": 29282.484375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.380167961120605, "min": 0.3424210250377655, "max": 12.380167961120605, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2414.1328125, "min": 66.42967987060547, "max": 2474.99462890625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07177783121562029, "min": 0.0636450168690941, "max": 0.07556785829736185, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28711132486248114, "min": 0.26316029923584533, "max": 0.36873717110275345, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20225745885103358, "min": 0.10099155768779491, "max": 0.27252115291707657, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8090298354041343, "min": 0.40396623075117966, "max": 1.3626057645853829, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.954545454545453, "min": 3.0454545454545454, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1098.0, "min": 134.0, "max": 1334.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.954545454545453, "min": 3.0454545454545454, "max": 24.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1098.0, "min": 134.0, "max": 1334.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687329181", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687329715" }, "total": 533.8971083230001, "count": 1, "self": 0.7580771909999839, "children": { "run_training.setup": { "total": 0.04565274499998395, "count": 1, "self": 0.04565274499998395 }, "TrainerController.start_learning": { "total": 533.0933783870001, "count": 1, "self": 0.7276800869966564, "children": { "TrainerController._reset_env": { "total": 5.606980474000011, "count": 1, "self": 5.606980474000011 }, "TrainerController.advance": { "total": 526.6045045990036, "count": 18200, "self": 0.3631848970082956, "children": { "env_step": { "total": 526.2413197019953, "count": 18200, "self": 382.51554916699195, "children": { "SubprocessEnvManager._take_step": { "total": 143.3896542610098, "count": 18200, "self": 2.2187795929904723, "children": { "TorchPolicy.evaluate": { "total": 141.17087466801934, "count": 18200, "self": 141.17087466801934 } } }, "workers": { "total": 0.3361162739935253, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 531.0506072439842, "count": 18200, "is_parallel": true, "self": 245.49433549297817, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0066626939999423485, "count": 1, "is_parallel": true, "self": 0.004217447999963042, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024452459999793064, "count": 10, "is_parallel": true, "self": 0.0024452459999793064 } } }, "UnityEnvironment.step": { "total": 0.05333493400007683, "count": 1, "is_parallel": true, "self": 0.0006024299999580762, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004290489999903002, "count": 1, "is_parallel": true, "self": 0.0004290489999903002 }, "communicator.exchange": { "total": 0.05016623000005893, "count": 1, "is_parallel": true, "self": 0.05016623000005893 }, "steps_from_proto": { "total": 0.0021372250000695203, "count": 1, "is_parallel": true, "self": 0.0003836159999082156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017536090001613047, "count": 10, "is_parallel": true, "self": 0.0017536090001613047 } } } } } } }, "UnityEnvironment.step": { "total": 285.5562717510061, "count": 18199, "is_parallel": true, "self": 11.3322376380072, "children": { "UnityEnvironment._generate_step_input": { "total": 6.071122734993537, "count": 18199, "is_parallel": true, "self": 6.071122734993537 }, "communicator.exchange": { "total": 227.53624395299437, "count": 18199, "is_parallel": true, "self": 227.53624395299437 }, "steps_from_proto": { "total": 40.616667425010974, "count": 18199, "is_parallel": true, "self": 7.892833901034805, "children": { "_process_rank_one_or_two_observation": { "total": 32.72383352397617, "count": 181990, "is_parallel": true, "self": 32.72383352397617 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013462499987326737, "count": 1, "self": 0.00013462499987326737, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 522.1502210770176, "count": 529763, "is_parallel": true, "self": 11.86697866694135, "children": { "process_trajectory": { "total": 291.0806352610764, "count": 529763, "is_parallel": true, "self": 289.8124667440766, "children": { "RLTrainer._checkpoint": { "total": 1.2681685169998218, "count": 4, "is_parallel": true, "self": 1.2681685169998218 } } }, "_update_policy": { "total": 219.20260714899985, "count": 90, "is_parallel": true, "self": 81.45421900900271, "children": { "TorchPPOOptimizer.update": { "total": 137.74838813999713, "count": 4587, "is_parallel": true, "self": 137.74838813999713 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15407860200002688, "count": 1, "self": 0.0008524039999429078, "children": { "RLTrainer._checkpoint": { "total": 0.15322619800008397, "count": 1, "self": 0.15322619800008397 } } } } } } }